Search Results for author:
Found 8 papers, 5 papers with code
Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics
We propose that perturbations in SAM perform perturbed forgetting, where they discard undesirable model biases to exhibit learning signals that generalize better.
SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision
Using SPARO, we demonstrate improvements on downstream recognition, robustness, retrieval, and compositionality benchmarks with CLIP (up to +14% for ImageNet, +4% for SugarCrepe), and on nearest neighbors and linear probe for ImageNet with DINO (+3% each).
On the Compositional Generalization Gap of In-Context Learning
In this work, we look at the gap between the in-distribution (ID) and out-of-distribution (OOD) performance of such models in semantic parsing tasks with in-context learning.
Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
Simplicial Embeddings (SEM) are representations learned through self-supervised learning (SSL), wherein a representation is projected into $L$ simplices of $V$ dimensions each using a softmax operation.
Fortuitous Forgetting in Connectionist Networks
Forgetting is often seen as an unwanted characteristic in both human and machine learning.
Iterated learning for emergent systematicity in VQA
Although neural module networks have an architectural bias towards compositionality, they require gold standard layouts to generalize systematically in practice.
GAIT: A Geometric Approach to Information Theory
We advocate the use of a notion of entropy that reflects the relative abundances of the symbols in an alphabet, as well as the similarities between them.
Grounded Recurrent Neural Networks
In this work, we present the Grounded Recurrent Neural Network (GRNN), a recurrent neural network architecture for multi-label prediction which explicitly ties labels to specific dimensions of the recurrent hidden state (we call this process "grounding").
